ArgumentError with no message, trying to reproduce the SavedModel CAPTCHA example

I'm trying to get something very similar to the CAPTCHA example. I built and saved a very simple model in Python using the high-level Estimator API (DNNClassifier). It takes 2 floats and outputs one of two classes. I'm trying to load it in Ruby and make a prediction with it.

I saved it using export_saved_model:

features = {'Float_input_1': tf.placeholder(tf.float32, shape=[1]),
            'Float_input_2': tf.placeholder(tf.float32, shape=[1])}
serving_input_receiver_fn = tf.estimator.export.build_raw_serving_input_receiver_fn(features, default_batch_size=None)
classifier.export_savedmodel(SAVED_MODEL_FOLDER + '_pb', serving_input_receiver_fn, strip_default_attrs=True)

Looking at my saved model using saved_model_cli shows this:

MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:

signature_def['predict']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['Float_input_1'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1)
        name: Placeholder:0
    inputs['Float_input_2'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1)
        name: Placeholder_1:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['class_ids'] tensor_info:
        dtype: DT_INT64
        shape: (-1, 1)
        name: dnn/head/predictions/ExpandDims:0
    outputs['classes'] tensor_info:
        dtype: DT_STRING
        shape: (-1, 1)
        name: dnn/head/predictions/str_classes:0
    outputs['logistic'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 1)
        name: dnn/head/predictions/logistic:0
    outputs['logits'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 1)
        name: dnn/logits/BiasAdd:0
    outputs['probabilities'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, 2)
        name: dnn/head/predictions/probabilities:0
  Method name is: tensorflow/serving/predict

My Ruby code:

saved_model = Tensorflow::Savedmodel.new
saved_model.LoadSavedModel('saved_model_pb', ['serve'], nil)

input = [0.97, 1.00]
feature1_output = saved_model.graph.operation('Placeholder').output(0)
feature2_output = saved_model.graph.operation('Placeholder_1').output(0)
classes = saved_model.graph.operation('dnn/head/predictions/str_classes').output(0)
# probabilities = saved_model.graph.operation('dnn/head/predictions/probabilities').output(0)

feature1_tensor = Tensorflow::Tensor.new(input[0])
feature2_tensor = Tensorflow::Tensor.new(input[1])
feeds_tensor_to_output_hash = {feature1_output => feature1_tensor,
                               feature2_output => feature2_tensor}
out_tensor = saved_model.session.run(feeds_tensor_to_output_hash, [classes], [])

puts out_tensor

This fails with an ArgumentError without an error message:

2018-05-22 17:07:08.443115: I tensorflow/cc/saved_model/loader.cc:242] Loading SavedModel with tags: { serve }; from: saved_model_pb/saved_model
2018-05-22 17:07:08.447053: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.2 AVX AVX2 FMA
2018-05-22 17:07:08.452575: I tensorflow/cc/saved_model/loader.cc:161] Restoring SavedModel bundle.
2018-05-22 17:07:08.453012: I tensorflow/cc/saved_model/loader.cc:171] The specified SavedModel has no variables; no checkpoints were restored.
2018-05-22 17:07:08.453024: I tensorflow/cc/saved_model/loader.cc:196] Running LegacyInitOp on SavedModel bundle.
2018-05-22 17:07:08.475575: I tensorflow/cc/saved_model/loader.cc:291] SavedModel load for tags { serve }; Status: success. Took 33095 microseconds.
rake aborted!
ArgumentError: 
.rbenv/versions/2.2.5/lib/ruby/gems/2.2.0/bundler/gems/tensorflow.rb-eb3f5bf4f0fd/lib/tensorflow/session.rb:57:in `Session_run'
.rbenv/versions/2.2.5/lib/ruby/gems/2.2.0/bundler/gems/tensorflow.rb-eb3f5bf4f0fd/lib/tensorflow/session.rb:57:in `run'
lib/tasks/ml.rake:380:in `block (2 levels) in <top (required)>'

Any idea what I'm doing wrong? The CAPTCHA example and model work fine. I've attached the saved model.

somaticio / tensorflow.rb

ArgumentError with no message, trying to reproduce the SavedModel CAPTCHA example #107